Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only flag non-read-only, open-world, non-idempotent, non-destructive. The description adds real behavior: this is an asynchronous job ('A job, like vids_create_video'), it returns the entire longer clip rather than just the delta, and 'uses only the added seconds' hints at how consumption/billing is scoped. It stops short of saying how to poll for completion or what the job result looks like.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences with the size constraint front-loaded and no filler; the endpoint hint at the end is low value but harmless. Minor compression ('3-10 s', 'uses only the added seconds') leaves a little ambiguity about whether that phrase refers to billing, sampling, or prompt scope.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a five-parameter async mutation with no output schema, the description covers the important pieces: job semantics, what is returned, the length ceiling, account scoping, and iteration. It omits how the caller retrieves the result, though the schema's mediaId text points to vids_get_job, which partially compensates.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so all five parameters (prompt, mediaId, duration, resolution, aspectRatio) are already documented, including defaults and enums. The description adds only the derived constraint that the source clip can be up to 24 s and the total can reach ~34 s, which is useful context but not parameter-level semantics beyond the schema; baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource ('Add 3-10 s to a generated clip'), plus concrete scope limits (source up to 24 s, output at most ~34 s). It does not explicitly contrast with the closest siblings, vids_edit_video and vids_upscale_video, so an agent must infer which one to pick when the intent is 'change an existing video'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the key operating context: run on the same account, and 'Call it again on the result to go longer, up to that limit,' which tells the agent how to chain calls for longer output. It gives no explicit when-not guidance versus vids_edit_video or vids_create_video as a fresh generation alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.